CN105824420B - A kind of gesture identification method based on acceleration transducer - Google Patents
A kind of gesture identification method based on acceleration transducer Download PDFInfo
- Publication number
- CN105824420B CN105824420B CN201610159248.1A CN201610159248A CN105824420B CN 105824420 B CN105824420 B CN 105824420B CN 201610159248 A CN201610159248 A CN 201610159248A CN 105824420 B CN105824420 B CN 105824420B
- Authority
- CN
- China
- Prior art keywords
- gesture
- acceleration
- data
- axis
- angle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/033—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor
- G06F3/0346—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
Abstract
The invention discloses a kind of gesture identification methods based on acceleration transducer, belong to technical field of hand gesture recognition.The present invention obtains gesture identification method in calculating process, can automatic decision action beginning and end.Extraneous control intervention is not needed.The present invention divides three steps (angle, feature, state) gradually to exclude non-compliant gesture, reduces overall calculation amount, while also reducing the probability of maloperation.The action planting modes on sink characteristic of the present invention is obtained by acquiring a large amount of gesture samples, is inputted by system, cannot voluntarily be adjusted setting by user's individual.Although requiring height to the feature difference of gesture in this way, calculation amount is small, and discrimination is high, improves the real-time of algorithm, quick identification can be reached with low cost.
Description
Technical field
The invention belongs to technical field of hand gesture recognition, more particularly to a kind of gesture identification side based on acceleration transducer
Method.
Background technology
For intelligent wearable device as one of currently manufactured field forward position direction, the movement including gesture identification identifies quilt
It is widely used in intelligent wearable device, acceleration transducer is applied to technical field of hand gesture recognition, by analyzes human hand gesture
Generated acceleration signal is detected, identifies the motion state of user and realizes operation to smart machine when movement.
However current acceleration transducer be applied in gesture identification field there is cannot accurate judgement action terminal
(or needing manual setting) cannot judge to filter out non-compliant gesture, cause the shortcomings of maloperation well.
Invention content
It is an object of the invention to overcome above-mentioned shortcoming and deficiency existing in the prior art, provide a kind of based on acceleration
The gesture identification method of sensor.
The purpose of the invention is achieved by the following technical solution:A kind of gesture identification method based on acceleration transducer,
Include the following steps:
(1) acceleration information and angular velocity data of user's hand motion are acquired by sensor;
(2) Kalman filtering is carried out to the data of step (1) acquisition, removes shaking interference and sensor during gesture
Clutter;
(3) border detection acted utilizes the correlation of gesture motion and acceleration change amount, automatic decision action
Terminal, and intercept judgement gesture of this section of action data as this;
(4) high-pass filtering and low-pass filtering are carried out to the action data of step (3) interception, filters out non-gesture motion number
According to further rejecting interference;
(5) Attitude Calculation, the angle of sensor and ground level when calculating movement according to sensing data obtain posture number
According to, and exclude according to angle the maloperation gesture of direction exception;
(6) compared according to the gesture motion feature in angular velocity data, acceleration information and attitude data, with maneuver library
It is right, confirm gesture whether effectively and gesture-type;
(7) gesture control device of the algorithmic match has a variety of working conditions;According to the current state of device, if hand
Gesture is effective, then sends out corresponding instruction;Gesture same in this way represents different instruction under different conditions, can effectively reduce gesture number
Amount is also convenient for user's memory convenient for identification.
When step (1) gathered data, acceleration information is sampled at a fixed time interval.
The step (2) uses Kalman filtering (Kalman filtering), right in the case of known measurement variance
The collected data of sensor carry out real-time update, calculate the optimal solution of current truthful data, filter out hand during gesture
The trueness error of shake and sensor hardware itself.
The step (3) uses the boundary detection method based on acceleration change amount, calculation as follows:
1) the x, y, z axis linear acceleration (filtering out gravity influence) of each sampled point is first calculated separately,
Wherein, aoxi、aoyi、aoziX, y, z axle acceleration data, g are measured for ith sample pointxi、gyi、gziFor the sampling
Component of the point acceleration of gravity in x, y, z axis;
2) the sum of the acceleration difference absolute value of ith sample point Δ a is calculatedi,
Δai=abS (axi--ax(i-1))+abS(ayi-ay(i-1))+abS(azi-az(i-1))
3) it is sampled data number, M to define NthFor the detection threshold of beginning and end:
IfThen i is gesture starting point;
IfAnd when having starting point, then i is gesture terminal.
The preliminary filter type of the step (4), when first investigating the acceleration change amount of all gestures in maneuver library, action
Between length maximum value and minimum value, using borders rule, the action data being truncated in step (3) is done and is judged, is lost
Discard the data not within the scope of this maximum value and minimum value.
The Attitude Calculation of the step (5), calculation are as follows:The first component according to acceleration of gravity on x, y, z axis
gx、gy、gz, it is converted into the quaternary number q=[w, x, y, z] for indicating sensor rotation angleπ(or can quaternary directly be exported by sensor
Number);Sensor and the angle on ground are calculated further according to quaternary number q, is yaw angle ψ (z-axis), pitching angle theta (y-axis), cross respectively
Roll angle(x-axis):
If the angular range of current gesture is within a preset range, this data is brought into next step.
Gesture motion in the step (6) in maneuver library, is distinguished based on following characteristics point:
1. the maximum value in acceleration change value and minimum value:The acceleration calculated in step (3) is poor
Divide the sum of absolute value Δ aiMaximum value and minimum value;
2. gesture time length L:L=tTerminal time-tStarting time;
3. the acceleration change value of three axis direction of x, y, z, and determine the wherein maximum axis of acceleration change:
Wherein, L is the time span of gesture;
4. the angular speed changing value of three axis direction of x, y, z, and determine that wherein angular speed changes maximum axis:
Wherein, ψ, θ of each sampled point,The yaw angle ψ (z-axis) that is calculated as in step (5), pitching angle theta (y-axis),
Roll angle(x-axis);
5. each inswept angle on three axis of x, y, z:
6. acceleration change wave crest number Px、Py、Pz:In gesture boundary, acceleration wave that equipment occurs on x, y, z axis
Peak number;
7. angular speed changes wave crest number Pψ、Pθ、In gesture boundary, angular speed wave that equipment occurs on x, y, z axis
Peak number;
For the data that step (5) obtains, compared item by item by the sequence of above-mentioned 7 characteristic points;If with maneuver library
In all characteristic points of some gesture all meet, then be determined as the gesture, stop technology process;The action being consistent such as is can not find,
Then judge that the gesture is invalid, stop technology process.
Characteristic in the maneuver library, the gesture sample by acquiring different conditions, Different Individual obtains, by system
Input, cannot voluntarily adjust setting by user's individual;The program requires height to the feature difference of gesture, but calculation amount is small, knows
Rate is not high, need not be adapted to for single individual, quick identification can be reached with low cost.
The present invention has the following advantages and effects with respect to the prior art:
1. in calculating process, can automatic decision action beginning and end.Extraneous control intervention is not needed.
2. point three steps (angle, feature, state) gradually exclude non-compliant gesture, reduce overall calculation amount,
The probability of maloperation is also reduced simultaneously.
It is obtained 3. acting planting modes on sink characteristic by acquiring a large amount of gesture samples, is inputted, cannot be voluntarily adjusted by user's individual by system
Whole setting.Although requiring height to the feature difference of gesture in this way, calculation amount is small, and discrimination is high, improves the real-time of algorithm
Property, quick identification can be reached with low cost.
4. the gesture control device of the algorithmic match has a variety of working conditions, same gesture represents under different conditions
Instruction it is different.Gesture quantity can be reduced in this way, can just solve " the feature difference requirement of gesture described in the 3rd article
It is high " the problem of, convenient for calculating identification, it is also convenient for user's memory.
Description of the drawings
Fig. 1 is the gesture identification method flow chart the present invention is based on acceleration transducer.
Fig. 2 is result figure of the step of the present invention (3) using the boundary detection method based on acceleration change amount;Wherein, A is
Starting point, B are terminal.
Specific implementation mode
Present invention will now be described in further detail with reference to the embodiments and the accompanying drawings, but embodiments of the present invention are unlimited
In this.
Embodiment 1
As shown in Figure 1, the present invention provides a kind of gesture identification methods based on acceleration transducer, including walk as follows
Suddenly:
(1) acceleration information and angular velocity data of user's hand motion are acquired by sensor;
(2) Kalman filtering is carried out to the data of step (1) acquisition, removes shaking interference and sensor during gesture
Clutter;
(3) border detection acted utilizes the correlation of gesture motion and acceleration change amount, automatic decision action
Terminal, and intercept judgement gesture of this section of action data as this;
(4) high-pass filtering and low-pass filtering are carried out to the action data of step (3) interception, filters out non-gesture motion number
According to further rejecting interference;
(5) Attitude Calculation, the angle of sensor and ground level when calculating movement according to sensing data obtain posture number
According to, and exclude according to angle the maloperation gesture of direction exception;
(6) compared according to the gesture motion feature in angular velocity data, acceleration information and attitude data, with maneuver library
It is right, confirm gesture whether effectively and gesture-type;
(7) gesture control device of the algorithmic match has a variety of working conditions;According to the current state of device, if hand
Gesture is effective, then sends out corresponding instruction;Gesture same in this way represents different instruction under different conditions, can effectively reduce gesture number
Amount is also convenient for user's memory convenient for identification.
When step (1) gathered data, acceleration information is sampled at a fixed time interval.
The step (2) uses Kalman filtering (Kalman filtering), right in the case of known measurement variance
The collected data of sensor carry out real-time update, calculate the optimal solution of current truthful data, filter out hand during gesture
The trueness error of shake and sensor hardware itself.
The step (3) uses the boundary detection method based on acceleration change amount, analysis chart as shown in Figure 2, calculating side
Formula is as follows:
1) the x, y, z axis linear acceleration (filtering out gravity influence) of each sampled point is first calculated separately,
Wherein, aoxi、aoyi、aoziX, y, z axle acceleration data, g are measured for ith sample pointxi、gyi、gziFor the sampling
Component of the point acceleration of gravity in x, y, z axis;
2) the sum of the acceleration difference absolute value of ith sample point Δ a is calculatedi,
Δai=abS (axi--ax(i-1))+abS(ayi-ay(i-1))+abS(azi-az(i-1))
3) it is sampled data number, M to define NthFor the detection threshold of beginning and end:
IfThen i is gesture starting point;
IfAnd when having starting point, then i is gesture terminal.
The preliminary filter type of the step (4), when first investigating the acceleration change amount of all gestures in maneuver library, action
Between length maximum value and minimum value, using borders rule, the action data being truncated in step (3) is done and is judged, is lost
Discard the data not within the scope of this maximum value and minimum value.
The Attitude Calculation of the step (5), calculation are as follows:The first component according to acceleration of gravity on x, y, z axis
gx、gy、gz, it is converted into the quaternary number q=[w, x, y, z] for indicating sensor rotation angleπ(or can quaternary directly be exported by sensor
Number);Sensor and the angle on ground are calculated further according to quaternary number q, is yaw angle ψ (z-axis), pitching angle theta (y-axis), cross respectively
Roll angle(x-axis):
If the angular range of current gesture is within a preset range, this data is brought into next step.
Gesture motion in the step (6) in maneuver library, is distinguished based on following characteristics point:
1. the maximum value in acceleration change value and minimum value:The acceleration difference absolute value calculated i.e. in step (3) it
With Δ aiMaximum value and minimum value;
2. gesture time length L:L=tTerminal time-tStarting time;
3. the acceleration change value of three axis direction of x, y, z, and determine the wherein maximum axis of acceleration change:
Wherein, L is the time span of gesture;
4. the angular speed changing value of three axis direction of x, y, z, and determine that wherein angular speed changes maximum axis:
Wherein, ψ, θ of each sampled point,The yaw angle ψ (z-axis) that is calculated as in step (5), pitching angle theta (y-axis),
Roll angle(x-axis);
5. each inswept angle on three axis of x, y, z:
6. acceleration change wave crest number Px、Py、Pz:In gesture boundary, acceleration wave that equipment occurs on x, y, z axis
Peak number;
7. angular speed changes wave crest numberIn gesture boundary, the angle that equipment occurs on x, y, z axis is fast
Spend wave crest number;
For the data that step (5) obtains, compared item by item by the sequence of above-mentioned 7 characteristic points;If with maneuver library
In all characteristic points of some gesture all meet, then be determined as the gesture, stop technology process;The action being consistent such as is can not find,
Then judge that the gesture is invalid, stop technology process.
Characteristic in the maneuver library, the gesture sample by acquiring different conditions, Different Individual obtains, by system
Input, cannot voluntarily adjust setting by user's individual;The program requires height to the feature difference of gesture, but calculation amount is small, knows
Rate is not high, need not be adapted to for single individual, quick identification can be reached with low cost.
The present invention has the following advantages and effects with respect to the prior art:
1. in calculating process, can automatic decision action beginning and end.Extraneous control intervention is not needed.
2. point three steps (angle, feature, state) gradually exclude non-compliant gesture, reduce overall calculation amount,
The probability of maloperation is also reduced simultaneously.
It is obtained 3. acting planting modes on sink characteristic by acquiring a large amount of gesture samples, is inputted, cannot be voluntarily adjusted by user's individual by system
Whole setting.Although requiring height to the feature difference of gesture in this way, calculation amount is small, and discrimination is high, improves the real-time of algorithm
Property, quick identification can be reached with low cost.
4. the gesture control device of the algorithmic match has a variety of working conditions, same gesture represents under different conditions
Instruction it is different.Gesture quantity can be reduced in this way, just solved " feature difference of gesture requires high " described in the 3rd article
Problem is also convenient for user's memory convenient for calculating identification.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, it is other it is any without departing from the spirit and principles of the present invention made by changes, modifications, substitutions, combinations, simplifications,
Equivalent substitute mode is should be, is included within the scope of the present invention.
Claims (6)
1. a kind of gesture identification method based on acceleration transducer, it is characterised in that:Include the following steps:
(1) acceleration information and angular velocity data of user's hand motion are acquired by sensor;
(2) Kalman filtering is carried out to the data of step (1) acquisition, the shaking interference and sensor during removal gesture are miscellaneous
Wave;
(3) border detection acted, using the correlation of gesture motion and acceleration change amount, automatic decision action rises
Stop, and intercept judgement gesture of this section of action data as this;
(4) high-pass filtering and low-pass filtering are carried out to the action data of step (3) interception, filters out non-gesture motion data, into
One step rejects interference;
(5) Attitude Calculation, the angle of sensor and ground level when calculating movement according to sensing data obtain attitude data,
And the maloperation gesture of direction exception is excluded according to angle;
(6) it according to angular velocity data, acceleration information and attitude data, is compared with the gesture motion feature in maneuver library,
Confirm gesture whether effectively and gesture-type;
(7) the matched gesture control device of this method has a variety of working conditions;According to the current state of device, if gesture has
Effect, then send out corresponding instruction;Gesture same in this way represents different instruction under different conditions,
Gesture motion in the step (6) in maneuver library, is distinguished based on following characteristics point:
1. the maximum value in acceleration change value and minimum value:The sum of the acceleration difference absolute value calculated in step (3) Δ aj
Maximum value and minimum value;
2. gesture time length L:L=tTerminal time-tStarting time;
3. the acceleration change value of three axis direction of x, y, z, and determine the wherein maximum axis of acceleration change:
Wherein, L is the time span of gesture;
4. the angle change value of three axis direction of x, y, z, and determine the wherein maximum axis of angle change:
Wherein, ψ, θ of each sampled point,The yaw angle ψ of z-axis that is calculated as in step (5), the pitching angle theta of y-axis, x-axis
Roll angle
5. each inswept angle on three axis of x, y, z:
6. acceleration change wave crest number Px、Py、Pz:In gesture boundary, acceleration wave peak number that equipment occurs on x, y, z axis;
7. angular speed changes wave crest number Pψ、Pθ、In gesture boundary, angular speed wave crest number that equipment occurs on x, y, z axis;
For the data that step (5) obtains, compared item by item by the sequence of above-mentioned 7 characteristic points;If with certain in maneuver library
All characteristic points of a gesture all meet, then are determined as the gesture, stop technology process;The action being consistent such as is can not find, then is sentenced
The gesture of breaking is invalid, stop technology process;Characteristic in the maneuver library, by acquiring different conditions, Different Individual
Gesture sample obtains, and is inputted by system, cannot voluntarily adjust setting by user's individual.
2. the gesture identification method according to claim 1 based on acceleration transducer, it is characterised in that:The step
(1) when gathered data, acceleration information is sampled at a fixed time interval.
3. the gesture identification method according to claim 1 based on acceleration transducer, it is characterised in that:The step
(2) Kalman filtering is used, in the case of known measurement variance, to the collected data of sensor, real-time update is carried out, calculates
The optimal solution for going out current truthful data filters out the shake of hand and the trueness error of sensor hardware itself during gesture.
4. the gesture identification method according to claim 1 based on acceleration transducer, it is characterised in that:The step
(3) use the boundary detection method based on acceleration change amount, calculation as follows:
1) the x, y, z axis linear acceleration that each sampled point filters out gravity influence is first calculated separately,
Wherein, aoxj、aoyj、aozjX, y, z axle acceleration data, g are measured for j-th of sampled pointxj、gyj、gzjFor the sampled point weight
Component of the power acceleration in x, y, z axis;
2) the sum of the acceleration difference absolute value of j-th of sampled point Δ a is calculatedj,
Δaj=abs (axj-ax(j-1))+abs(ayj-ay(j-1))+abs(azj-az(j-1))
3) it is sampled data number, M to define NthFor the detection threshold value of beginning and end:
IfThen j is gesture starting point;
IfAnd when having starting point, then j is gesture terminal.
5. the gesture identification method according to claim 1 based on acceleration transducer, it is characterised in that:The step
(4) preliminary filter type, first investigate maneuver library in the acceleration change amount of all gestures, the maximum value of actuation time length and
Minimum value is done the action data being truncated in step (3) and is judged, discard not in this maximum value using borders rule
With the data within the scope of minimum value.
6. the gesture identification method according to claim 1 based on acceleration transducer, it is characterised in that:The step
(5) Attitude Calculation, calculation are as follows:The first component g according to acceleration of gravity on x, y, z axisx、gy、gz, it is converted into table
Show the quaternary number q=[w, x, y, z] at sensor rotation angleπ;Sensor and the angle on ground are calculated further according to quaternary number q, point
Be not the yaw angle ψ of z-axis, the pitching angle theta of y-axis, x-axis roll angle
If the angular range of current gesture is within a preset range, this data is brought into next step.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610159248.1A CN105824420B (en) | 2016-03-21 | 2016-03-21 | A kind of gesture identification method based on acceleration transducer |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610159248.1A CN105824420B (en) | 2016-03-21 | 2016-03-21 | A kind of gesture identification method based on acceleration transducer |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105824420A CN105824420A (en) | 2016-08-03 |
CN105824420B true CN105824420B (en) | 2018-09-14 |
Family
ID=56524667
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610159248.1A Active CN105824420B (en) | 2016-03-21 | 2016-03-21 | A kind of gesture identification method based on acceleration transducer |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105824420B (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106372673A (en) * | 2016-09-06 | 2017-02-01 | 深圳市民展科技开发有限公司 | Apparatus motion identification method |
CN106990841A (en) * | 2017-03-30 | 2017-07-28 | 无锡云瞳信息科技有限公司 | Gesture identification method and the wearable video camera of intelligence based on motion sensor |
CN108960016A (en) * | 2017-05-25 | 2018-12-07 | 富士通株式会社 | The method and apparatus for detecting specific action |
CN108108015A (en) * | 2017-11-20 | 2018-06-01 | 电子科技大学 | A kind of action gesture recognition methods based on mobile phone gyroscope and dynamic time warping |
CN109262608A (en) * | 2018-08-22 | 2019-01-25 | 南京阿凡达机器人科技有限公司 | A kind of method and system that remote-controlled robot is grappled |
CN111259694B (en) * | 2018-11-30 | 2021-02-12 | 北京字节跳动网络技术有限公司 | Gesture moving direction identification method, device, terminal and medium based on video |
CN109883531A (en) * | 2019-03-05 | 2019-06-14 | 广州亚美信息科技有限公司 | Vehicle vibration kind identification method and system based on acceleration transducer |
CN110187772B (en) * | 2019-06-03 | 2020-09-25 | 中国科学院电子学研究所 | Clapping gesture recognition method |
CN110377159B (en) * | 2019-07-24 | 2023-06-09 | 张洋 | Action recognition method and device |
CN113655879A (en) * | 2021-07-15 | 2021-11-16 | 上海交通大学 | Gesture recognition method and system based on accelerometer |
CN115695518B (en) * | 2023-01-04 | 2023-06-30 | 广东保伦电子股份有限公司 | PPT control method based on intelligent mobile equipment |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104185050A (en) * | 2014-07-30 | 2014-12-03 | 哈尔滨工业大学深圳研究生院 | OTT television based intelligent remote control system and control method thereof |
CN104731307A (en) * | 2013-12-20 | 2015-06-24 | 孙伯元 | Somatic action identifying method and man-machine interaction device |
CN104866099A (en) * | 2015-05-27 | 2015-08-26 | 东南大学 | Error compensation method for improving gesture identification precision of intelligent device based on motion sensor |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101185144B1 (en) * | 2006-01-24 | 2012-09-24 | 삼성전자주식회사 | Method and apparatus for estimating 2-dimension trajectory of a gesture |
-
2016
- 2016-03-21 CN CN201610159248.1A patent/CN105824420B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104731307A (en) * | 2013-12-20 | 2015-06-24 | 孙伯元 | Somatic action identifying method and man-machine interaction device |
CN104185050A (en) * | 2014-07-30 | 2014-12-03 | 哈尔滨工业大学深圳研究生院 | OTT television based intelligent remote control system and control method thereof |
CN104866099A (en) * | 2015-05-27 | 2015-08-26 | 东南大学 | Error compensation method for improving gesture identification precision of intelligent device based on motion sensor |
Non-Patent Citations (1)
Title |
---|
基于加速度传感器的手势识别;代宏斌;《中国优秀硕士学位论文全文数据库》;20140915(第9期);第9-27页 * |
Also Published As
Publication number | Publication date |
---|---|
CN105824420A (en) | 2016-08-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105824420B (en) | A kind of gesture identification method based on acceleration transducer | |
US9221170B2 (en) | Method and apparatus for controlling a robotic device via wearable sensors | |
CN109579853B (en) | Inertial navigation indoor positioning method based on BP neural network | |
US20190065872A1 (en) | Behavior recognition apparatus, learning apparatus, and method and program therefor | |
CN111666891B (en) | Method and device for estimating movement state of obstacle | |
CN105877757A (en) | Multi-sensor integrated human motion posture capturing and recognizing device | |
CN111611901B (en) | Vehicle reverse running detection method, device, equipment and storage medium | |
EP2975867A1 (en) | Method for detecting driving events of a vehicle based on a smartphone | |
CN110057380B (en) | Step counting method, step counting device, terminal and storage medium | |
CN106184220B (en) | Abnormal driving detection method in a kind of track based on vehicle location track | |
CN111095164A (en) | Method and apparatus for detecting user input in dependence on gesture | |
CN110327050B (en) | Embedded intelligent detection method for falling state of person for wearable equipment | |
CN107766930B (en) | Equivalent ROM distance calculation method based on DTW cluster fuzzy clustering SOM neurons | |
JP2019112049A (en) | Method for recognizing driving style of driver of land vehicle and corresponding device | |
CN109540143B (en) | Pedestrian unconventional action direction identification method based on multi-sensing-source dynamic peak fusion | |
CN107358248B (en) | Method for improving falling detection system precision | |
WO2019033587A1 (en) | Smart watch-based gps drifting filtering method, and smart watch | |
WO2017185222A1 (en) | System and method for motion trajectory collection and analysis based on ball games | |
CN107662613B (en) | A kind of extreme driving behavior recognition methods and system based on mobile intelligent perception | |
CN107203271B (en) | Double-hand recognition method based on multi-sensor fusion technology | |
CN108710828A (en) | The method, apparatus and storage medium and vehicle of identification object | |
CN108051001B (en) | Robot movement control method and system and inertial sensing control device | |
CN106408593A (en) | Video-based vehicle tracking method and device | |
CN106740865B (en) | A method of vehicle zig zag event is determined according to acceleration and gyroscope | |
CN110929766B (en) | Self-adaptive pedestrian mobile phone attitude identification method based on Gaussian mixture clustering algorithm |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20201022 Address after: No.242, dongshuangding village, Yaxi Town, Rongcheng City, Weihai City, Shandong Province Patentee after: Chen Ailian Address before: 518000 Guangdong city of Shenzhen province Baoan District Shengnawei Bay beauty garden 9A-2108 Patentee before: Li Xiao |
|
TR01 | Transfer of patent right |